• Journal of the Korea Society of Computer and Information
• /
• v.26 no.4
• /
• pp.161-168
• /
• 2021

In this paper, it is a system that informs people who take medication periodically to facilitate the convenience of the elderly and the disabled. It is a system that measures the full weight of pills that need to be taken for a week using a weight sensor, and then determines whether or not the pills are taken by measuring the weight of the reduced pills again when the user takes them. For people with disabilities who are unable to move, it includes the function of automatically transporting medicine to the user-set location at the time of use using a line tracer based autonomous vehicle. It is also configured to inform users who have not taken the pill through an alarm that includes visual and auditory functions at a specific time to inform them of this. This work attempts to help users take their medication without forgetting by segmenting the task performance process of such a system through simulations.

• International Journal of Computer Science & Network Security
• /
• v.21 no.6
• /
• pp.107-118
• /
• 2021

The deployment of 5G is in full swing, with a significant yearly growth in the data traffic expected to reach 26% by the year and data consumption to reach 122 EB per month by 2022 [10]. In parallel, the idea of smart cities has been implemented by various governments and private organizations. One of the main objectives of 5G deployment is to help develop and realize smart cities. 5G can support the enhanced data delivery requirements and the mass connection requirements of a smart city environment. However, for specific high-demanding applications like tactile Internet, transportation, and augmented reality, the cloud-based 5G infrastructure cannot deliver the required quality of services. We suggest using multi-access edge computing (MEC) technology for smart cities' environments to provide the necessary support. In cloud computing, the dependency on a central server for computation and storage adds extra cost in terms of higher latency. We present a few scenarios to demonstrate how the MEC, with its distributed architecture and closer proximity to the end nodes can significantly improve the quality of services by reducing the latency. This paper has surveyed the existing work in MEC for 5G and highlights various challenges and opportunities. Moreover, we propose a unique framework based on the use of MEC for 5G in a smart city environment. This framework works at multiple levels, where each level has its own defined functionalities. The proposed framework uses the MEC and introduces edge-sub levels to keep the computing infrastructure much closer to the end nodes.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.5
• /
• pp.1610-1629
• /
• 2021

Failures frequently occurred in manufacturing machines due to complex and changeable manufacturing environments, increasing the downtime and maintenance costs. This manuscript develops a novel deep learning-based method named Multi-Domain Convolutional Neural Network (MDCNN) to deal with this challenging task with vibration signals. The proposed MDCNN consists of time-domain, frequency-domain, and statistical-domain feature channels. The Time-domain channel is to model the hidden patterns of signals in the time domain. The frequency-domain channel uses Discrete Wavelet Transformation (DWT) to obtain the rich feature representations of signals in the frequency domain. The statistic-domain channel contains six statistical variables, which is to reflect the signals' macro statistical-domain features, respectively. Firstly, in the proposed MDCNN, time-domain and frequency-domain channels are processed by CNN individually with various filters. Secondly, the CNN extracted features from time, and frequency domains are merged as time-frequency features. Lastly, time-frequency domain features are fused with six statistical variables as the comprehensive features for identifying the fault. Thereby, the proposed method could make full use of those three domain-features for fault diagnosis while keeping high distinguishability due to CNN's utilization. The authors designed massive experiments with 10-folder cross-validation technology to validate the proposed method's effectiveness on the CWRU bearing data set. The experimental results are calculated by ten-time averaged accuracy. They have confirmed that the proposed MDCNN could intelligently, accurately, and timely detect the fault under the complex manufacturing environments, whose accuracy is nearly 100%.

• The Korea Journal of Herbology
• /
• v.34 no.6
• /
• pp.63-70
• /
• 2019

Objective : Arnebiae Radix, the roots of Arnebia euchroma (Royle) Johnst. or A. guttata Bunge, is a well-known traditional herbal medicine in East Asia. In the Korean Pharmacopoeia, three authentic species, including two Arnebia and Lithospermum erythrorhizon Sieb. et Zucc. have recognized as a Lithospermi Radix. But, the morphological and taxonomic information of two authentic Arnebia species lacks date since their distribution and difficulty of accessing the natural habitats. Methods : A full description of the external morphological characteristics of vegetative and reproductive organs in the original plants was carried out using digital calipers and stereoscope. For providing their taxonomic and nomenclatural synonyms, we reviewed various plant checklists and taxonomic literature. Results : This study provides taxonomic information of A. euchroma and A. guttata based on a morphological examination of authentic plant individuals and field observations. Detailed descriptions of the two Arnebia species, major quantitative and qualitative characteristics, nomenclatural reviews, distribution maps, and lists of voucher specimens examined are provided. The shape of leaves, root length, stem number, calyx length and pubescence as well as corolla color were useful characteristics for identification. Moreover, we confirmed that A. euchroma and A. guttata are clearly heterostylous species. Conclusion : Our research provides valuable basic information that could be used as quality control for distinguishing between Arnebiae Radix and its adulterants. These results will help in the understanding of authentic plants and also provide the verified materials and voucher information.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.2
• /
• pp.435-449
• /
• 2023

The state-of-the-art video-based point cloud compression(V-PCC) has a high efficiency of compressing 3D point cloud by projecting points onto 2D images. These images are then padded and compressed by High-Efficiency Video Coding(HEVC). Pixels in padded 2D images are classified into three groups including origin pixels, padded pixels and unoccupied pixels. Origin pixels are generated from projection of 3D point cloud. Padded pixels and unoccupied pixels are generated by copying values from origin pixels during image padding. For padded pixels, they are reconstructed to 3D space during geometry reconstruction as well as origin pixels. For unoccupied pixels, they are not reconstructed. The rate distortion optimization(RDO) used in HEVC is mainly aimed at keeping the balance between video distortion and video bitrates. However, traditional RDO is unreliable for padded pixels and unoccupied pixels, which leads to significant waste of bits in geometry reconstruction. In this paper, we propose a new RDO scheme which takes 3D-Distortion into account instead of traditional video distortion for padded pixels and unoccupied pixels. Firstly, these pixels are classified based on the occupancy map. Secondly, different strategies are applied to these pixels to calculate their 3D-Distortions. Finally, the obtained 3D-Distortions replace the sum square error(SSE) during the full RDO process in intra prediction and inter prediction. The proposed method is applied to geometry frames. Experimental results show that the proposed algorithm achieves an average of 31.41% and 6.14% bitrate saving for D1 metric in Random Access setting and All Intra setting on geometry videos compared with V-PCC anchor.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.168-170
• /
• 2022

The government enacted and promulgated the 'Severe Accident Punishment Act' in January 2021, and is enforcing the law for workplaces with 50 or more full-time workers. However, the number of industrial accident accidents in 2021 increased by 10.7% compared to the same period of the previous year, and chemical gas Safety accidents due to leaks and explosions also occur frequently. Therefore, in high-risk industrial sites, comprehensive Safety measures are urgently needed. In this study, BLE Mesh networking in industrial sites with poor communication environment apply technology. The complex sensor AIoT device recognizes a dangerous situation as a gas sensing value, voice, and motion value, and transmits it to the server. The server monitors the risk situation in real time through information value analysis and judgment through artificial intelligence LSTM algorithm and CNN algorithm for AIoT transmission information. Through this study, through the development of AIoT devices capable of gas sensing, voice and motion recognition, and AI-applied safety management systems, It will contribute to the expansion of the social safety net by expanding its application.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.3
• /
• pp.43-54
• /
• 2024

Recently, there has been a lot of research on utilizing Language Models, and Large Language Models have achieved innovative results in various tasks. However, the practical application faces limitations due to the constrained resources and costs required to utilize Large Language Models. Consequently, there has been recent attention towards methods to effectively utilize models within given resources. Curriculum Learning, a methodology that categorizes training data according to difficulty and learns sequentially, has been attracting attention, but it has the limitation that the method of measuring difficulty is complex or not universal. Therefore, in this study, we propose a methodology based on data heterogeneity-based Curriculum Learning that measures the difficulty of data using reliable prior information and facilitates easy utilization across various tasks. To evaluate the performance of the proposed methodology, experiments were conducted using 5,000 specialized documents in the field of information communication technology and 4,917 documents in the field of healthcare. The results confirm that the proposed methodology outperforms traditional fine-tuning in terms of classification accuracy in both LoRA fine-tuning and full fine-tuning.

• Journal of Radiation Industry
• /
• v.17 no.4
• /
• pp.391-396
• /
• 2023

Currently, state-of-the-art devices such as SPECT, PET/CT, and PET/MRI are rapidly spreading nationwide, and the penetration rate of nuclear medical devices is also ranked fifth in the world. However, PET/MRI's system is slower and less common because it is more complex than PET/CT. The purpose of this study is to provide optimal information on PET/MRI according to the patient's disease. The subjects obtained information on head and neck cancer, pediatric patients, breast cancer patients, heart disease patients, lung cancer patients, and rectal cancer patients. We tried to accumulate protocols by obtaining a lot of information about each disease. In diagnosing head and neck cancer, it is believed that it is highly likely to be used in evaluating preoperative stage determination, recurrence and remote metastasis after treatment, and unclear primary cervical lymph node metastasis. Diagnosis and continuous follow-up of pediatric patients can increase patient benefits by minimizing radiation exposure. Breast cancer provides a comprehensive evaluation of the clinical need to determine the extent of disease in breast and local lymph nodes and the systematic stages of early diagnosis or recurrence. In diagnosing heart disease patients, MR-based PET motion correction helps to realize the full potential of PET images. For lung cancer patients, the clinical value and usefulness of the resolution and detection ability of integrated PET/MRI for soft tissues such as lung cancer will be sufficient. In diagnosing rectal cancer patients, the detection of missing residual diseases can change the clinical response evaluation for rectal cancer patients treated with TNT, and both the initial stage and treatment response evaluation are possible. Therefore, this literature study provided basic clinical data for PET/MRI tests.

• Journal of the Korean Society for Library and Information Science
• /
• v.13
• /
• pp.95-119
• /
• 1986

The objective of this study is to search for a theoretical and practical solution to the question of what is the most effective and qualitative method of information service for the college and university libraries in Korea. Assuming the maximum service or total service theory in information services, therefore, it appears natural that the subject specialist who is highly knowledgeable in his subject is indispensable in raising the quality of information librarians. The procedure of this research was as follows: There was no college and university library employing any full-time subject spceialist in Korea. This research, however, was proceeded on the assumption that subject specialists are already employed in all of the college and university libraries after the subject specialist system is established. The least qualification of subject specialist is limited, based on the criteria given by the foreign literature, to those who have master's degree in Library Science and bachelor's degree in any other subject area, those who have bacholor's degree in Library Science and master's degree in any other subject area, or those who have both bacholor's and master's degrees in Library Science with minor in any subject field . To prove the research hypothesis that the subject specialist will perform his role more efficiently than the generalist in effectively providing information service based on both accuracy and speed, this research as an obtrusive testing method analyzed the effectiveness by presenting information questions to the generalists and subject specialists who are information librarians in college and university libraries. For this study 20 librarians working at 12 university libraries were tested for performance levels of information services. The result showed $59.75\%$ an absolute performance rate and $75.20\%$ an adjust performance rate. Compared to Thomas Childer's 1970 study in which he used the unobtrusive testing method, these results were $5\%$ higher in the absolute performance rate and $11.36\%$ higher in the adjust performance rate. In comparing the generalist with the subject specialist in efficiency of information service, while the absolute performance rate was $57.08\%$ and the adjust performance rate was $73.08\%$ in the case of the generalist, the absolute rate was $63.75\%$ and the adjust rate was $78.38\%$ in the case of specialist, therefore, the efficiency of the subject specialist was $6.67\%$ higher in the absolute performance rate and $5.30\%$ higher in the adjust performance rate than that of generalist. But the factor of speediness was excluded from the analysis because of the difference between the time the interviewers recorded and the time the interviewee recorded. On the basis of the result of this research, it should be desirable to educate subject specialists and employ them as information librarians and for them to function as efficient subject specialists in order to improve the effectiveness of information services, the nucleus of the raison d'etre of college and university libraries.

• Journal of Legislation Research
• /
• no.54
• /
• pp.155-192
• /
• 2018

As the 'hyper-connected society' has emerged through the 'Fourth Industrial Revolution, public interests as well as social dangers have increased. Above all, the risk of infringement of information, including confidential personal information, is dramatically increasing. As the hyper-connected society has been realized, even if only one of the internet devices is hacked, there would be a danger that the ripple effect of such a hacking spreads to the whole network. Therefore, the necessity and importance of information security, including cybersecurity, has been increasing. In other words, the stability of cyberspace and internet space is becoming more important. As a result, the Korean government is seeking to build a legal system related to information security, which would be able to cope with the information infringement problem in the hyper-connected society. However, it seems that the government is still struggling with the direction of building such a legal system. In this context, a comparative review examining the legal systems of advanced foreign countries will provide meaningful implications as to what kinds of legal policies we should devise and implement for information security. In particular, the U.S. legislative act that actively responds to the cybersecurity violations is worthy of reference. For this reason, this article systematically analyzes the current status of the U.S. cybersecurity laws. Especially, this article focuses on the "Cybersecurity Information Sharing Act of 2015"(hereinafter "CISA"), that was recently enacted by the U.S. congress. The CISA prescribes the systemic and detailed information-sharing between national and private entities. The CISA, that actively promotes information-sharing, is full of suggestions for us, in that information-sharing is an effective way to properly realize information security in today's hyper-connected society.